A Probabilistic Room Location Service for Wireless Networked Environments

Castro, Paul; Chiu, Patrick; Kremenek, Ted; Muntz, Richard R.

doi:10.1007/3-540-45427-6_3

Cited by 322 publications

(269 citation statements)

References 6 publications

Supporting

Mentioning

266

Contrasting

Unclassified

Order By: Relevance

“…We conclude this methodology section by proving the relationship between Kullback-Leibler divergence kernel regression for WiFi localisation and previous Bayesian probabilistic approaches to that problem such as (Castro et al, 2001;Roos et al, 2002). Assuming that we know the true fingerprint distributions q at every fingerprint location {x , y }, we can express the probability of observing a sequence of discrete, integer RSSI measurements S (expressed as a histogram {h 1 , h 2 , .…”

Section: Relationship Between Kl-divergence Kernels and Bayesian Methodsmentioning

confidence: 81%

“…The first usage of a probabilistic approach to RSSI in indoor localisation was explained in (Castro et al, 2001;Roos et al, 2002;Youssef et al, 2003). They proposed to model the distribution of RSSI at each fingerprint location as a histogram, and to use it as a prior in a Bayesian framework, to compute the probability of having a specific histogram of RSSI at a new location using Bayesian Networks (Castro et al, 2001;Roos et al, 2002) or the Naive Bayes algorithm (Youssef et al, 2003).…”

Section: Prior Art In Probability-based Indoor Localisationmentioning

confidence: 99%

“…They proposed to model the distribution of RSSI at each fingerprint location as a histogram, and to use it as a prior in a Bayesian framework, to compute the probability of having a specific histogram of RSSI at a new location using Bayesian Networks (Castro et al, 2001;Roos et al, 2002) or the Naive Bayes algorithm (Youssef et al, 2003). Paschalidis et al (2009) use a Kullback-Leibler-based statistical framework for Wireless Sensor Networks localisation (consisting in null hypothesis testing for each fingerprint).…”

Section: Prior Art In Probability-based Indoor Localisationmentioning

confidence: 99%

See 2 more Smart Citations

Probability kernel regression for WiFi localisation

Mirowski¹,

Whiting²,

Steck³

et al. 2012

Journal of Location Based Services

View full text Add to dashboard Cite

Various methods have been developed for indoor localisation using WLAN signals. Algorithms that fingerprint the Received Signal Strength Indication (RSSI) of WiFi for different locations can achieve tracking accuracies of the order of a few meters. RSSI fingerprinting suffers though from two main limitations: first, as the signal environment changes, so does the fingerprint database, which requires regular updates; second, it has been reported that, in practice, certain devices record more complex (e.g bimodal) distributions of WiFi signals, precluding algorithms based on the mean RSSI. Mirowski et al. (2011) have recently introduced a simple methodology that takes into account the full distribution for computing similarities among fingerprints using Kullback-Leibler divergence, and then performs localisation through kernel regression. Their algorithm provides a natural way of smoothing over time and motion trajectories and can be applied directly to histograms of WiFi connections to access points, ignoring RSSI distributions, hence removing the need for fingerprint recalibration. It has been shown to outperform nearest neighbours or Kalman and particle filters, achieving up to 1m accuracy in office environments. In this paper, we focus on the relevance of Gaussian or non-Gaussian distributions for modeling RSSI distributions by considering additional probabilistic kernels for comparing Gaussian distributions and by evaluating them on three contrasting datasets. We discuss their limitations and formulate how the KL-divergence kernel regression algorithm bridges the gap with other WiFi localisation algorithms, notably Bayesian networks, SVMs and K nearest neighbours. Finally, we revisit the assumptions on the fingerprint maps and overview practical WiFi localisation software implementation.

show abstract

Section: Relationship Between Kl-divergence Kernels and Bayesian Methodsmentioning

confidence: 81%

Section: Prior Art In Probability-based Indoor Localisationmentioning

confidence: 99%

Section: Prior Art In Probability-based Indoor Localisationmentioning

confidence: 99%

See 1 more Smart Citation

Probability kernel regression for WiFi localisation

Mirowski¹,

Whiting²,

Steck³

et al. 2012

Journal of Location Based Services

View full text Add to dashboard Cite

show abstract

“…The initial problems identified with Wi-Fi network localization are that it is not very accurate (up to 1-2 meters accuracy at best) and requires an understanding of the physical layout of the wireless environment. The problem of improving accuracy from RSSI values has been worked on by [9][10][11][12] and a number of algorithms have been proposed with varying results. The problem of the wireless physical environment is one that has been 'passed-off' by a number of commercial applications which put the burden of calibration on network administrators.…”

Section: Location Based Security and Servicesmentioning

confidence: 99%

Localization to Enhance Security and Services in Wi-Fi Networks under Privacy Constraints

Ayres¹,

Mehmood²,

Mitchell

et al. 2009

Lecture Notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering

View full text Add to dashboard Cite

Abstract. Developments of seamless mobile services are faced with two broad challenges, systems security and user privacy -access to wireless systems is highly insecure due to the lack of physical boundaries and, secondly, location based services (LBS) could be used to extract highly sensitive user information. In this paper, we describe our work on developing systems which exploit location information to enhance security and services under privacy constraints. We describe two complimentary methods which we have developed to track node location information within production University Campus Networks comprising of large numbers of users. The location data is used to enhance security and services. Specifically, we describe a method for creating geographic firewalls which allows us to restrict and enhance services to individual users within a specific containment area regardless of physical association. We also report our work on LBS development to provide visualization of spatio-temporal node distribution under privacy considerations.

show abstract

“…For phone cell, and other region-based location technologies it can often be difficult to describe the region that is sensed. For example, see [8] for a description of tracking accuracy using a 802.11-based system. For our work, we will be able to use any approximation to the location of the user since we use a sampling approach to visibility analysis…”

Section: Related Workmentioning

confidence: 99%

Filtering Location-Based Information Using Visibility

Beeharee

Steed

2005

Location- And Context-Awareness

View full text Add to dashboard Cite

Abstract. In this paper we present an approach for exploiting knowledge about features in the real world in order to compute visibility of buildings. This is performed with the awareness of the inconsistencies and lack of accuracy in both mapping technology and GPS positioning in urban spaces. Electronic tourist guide systems typically recommend locations and sometimes provide navigation information. We have augmented this system to exploit visibility knowledge about neighbouring physical features

show abstract

A Probabilistic Room Location Service for Wireless Networked Environments

Cited by 322 publications

References 6 publications

Probability kernel regression for WiFi localisation

Probability kernel regression for WiFi localisation

Localization to Enhance Security and Services in Wi-Fi Networks under Privacy Constraints

Filtering Location-Based Information Using Visibility

Contact Info

Product

Resources

About